Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2308 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.6313. Min Act: -0.0001

Data Index: 220619 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5931. Min Act: -0.0001

Data Index: 64189 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5487. Min Act: -0.0001

Data Index: 406548 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1005494 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5006. Min Act: -0.0001

Data Index: 942162 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5073. Min Act: -0.0001

Data Index: 185118 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5025. Min Act: -0.0001

Data Index: 641537 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4842. Min Act: -0.0001

Data Index: 819925 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4825. Min Act: -0.0001

Data Index: 222378 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4964. Min Act: -0.0001

Data Index: 170217 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.5126. Min Act: -0.0001

Data Index: 364790 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4924. Min Act: -0.0001

Data Index: 673733 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4714. Min Act: -0.0001

Data Index: 496558 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1164520 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4582. Min Act: -0.0001

Data Index: 764759 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4539. Min Act: -0.0001

Data Index: 1229279 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4641. Min Act: -0.0001

Data Index: 1215085 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4331. Min Act: -0.0001

Data Index: 817456 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4734. Min Act: -0.0001

Data Index: 588207 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.6313. Min Range: -0.6313

Max Act: 0.4595. Min Act: -0.0001

Data Index: 277601 (C4 (Web Text))

Max Activating Token Index: 581